Python · Apache-2.0
sutro-sh/jev-align
Build calibrated AI Functions from human feedback using Jev and GEPA.
★ 313
Stars
25 forks · 1 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
21.5
Momentum / 100
see the breakdown below
50d ago
Created
last push 11d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 14.3 | last push 11d ago; decays to zero at 180 days |
| Scale | 15 | 7.2 | 313 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 21.5 | capped at 35 because growth is unmeasured |
Detail
| Topics | active-learningclassificationcligepahuman-in-the-loopjevprompt-optimizationtypesafe-ai |
| Matched on | Dev Tools (cli) |
| Short window | +1 stars over 7 days = 0.1/day |
| Long window | +6 stars over 26 days = 0.2/day |
| Lifetime average | 6.60 stars/day over 47 days |
| First seen here | 2026-10-11 |
| Last read | 6d ago |